The research on medical image segmentation is of great significance in advancing efficient and accurate automated image processing techniques.To address the problem of inaccurate segmentation results caused by significant variations in organ tissue shapes and blurred boundaries present in medical images,a novel network named MFMANet is proposed.Built upon a"U"-shaped architecture,the network integrates multi-scale information fusion modules and multi-attention modules.Specifically,multi-scale information modules capture multi-scale information in the shallow layers of the network to bridge the semantic gap between encoder and decoder features,thereby enhancing the network's ability to handle large variations in organ sizes.Regarding the issue of blurred boundaries,multi-attention mechanism utilizes Swin Transformer as the deep encoder-decoder network,employing channel and spatial attention instead of traditional skip connections to achieve finer feature extraction.Experimental results on the ACDC and Synapse public datasets show that the proposed method achieves improvements of 1.51%and 1.29%in Dice similarity coefficient as compared with MTUNet,fully demonstrating its effectiveness in enhancing segmentation network accuracy.

The research on medical image segmentation is of great significance in advancing efficient and accurate automated image processing techniques.To address the problem of inaccurate segmentation results caused by significant variations in organ tissue shapes and blurred boundaries present in medical images,a novel network named MFMANet is proposed.Built upon a"U"-shaped architecture,the network integrates multi-scale information fusion modules and multi-attention modules.Specifically,multi-scale information modules capture multi-scale information in the shallow layers of the network to bridge the semantic gap between encoder and decoder features,thereby enhancing the network's ability to handle large variations in organ sizes.Regarding the issue of blurred boundaries,multi-attention mechanism utilizes Swin Transformer as the deep encoder-decoder network,employing channel and spatial attention instead of traditional skip connections to achieve finer feature extraction.Experimental results on the ACDC and Synapse public datasets show that the proposed method achieves improvements of 1.51%and 1.29%in Dice similarity coefficient as compared with MTUNet,fully demonstrating its effectiveness in enhancing segmentation network accuracy.

BK polyomavirus-associated nephropathy (BKPyVAN) is a common cause of allograft failure. However, differentiation between BKPyVAN and type I T cell-mediated rejection (TCMR) is challenging when simian virus 40 (SV40) staining is negative, because of the similarities in histopathology. This study investigated whether donor-derived cell-free DNA (ddcfDNA) can be used to differentiate BKPyVAN. Target region capture sequencing was applied to detect the ddcfDNAs of 12 recipients with stable graft function, 22 with type I TCMR, 21 with proven BKPyVAN, and 5 with possible PyVAN. We found that urinary ddcfDNA levels were upregulated in recipients with graft injury, whereas plasma ddcfDNA levels were comparable for all groups. The median urinary concentrations and fractions of ddcfDNA in proven BKPyVAN recipients were significantly higher than those in type I TCMR recipients (10.4 vs. 6.1 ng/mL,